Commit graph

31625 commits

Author SHA1 Message Date
Alexsander Hamir
c7ef6768be fix(prometheus): use return_exceptions=True for budget metric lookups
Make asyncio.gather resilient to partial failures. If key, team, or
user lookup raises, log at debug level and allow the others to
complete. Prevents one failing lookup from blocking the rest.
2026-02-05 15:43:13 -08:00
Alexsander Hamir
30534d7e82 perf(prometheus): parallelize budget metric lookups with asyncio.gather
Replace sequential await of key, team, and user budget metric lookups
with asyncio.gather() so they run in parallel. Reduces latency from
T_key + T_team + T_user to max(T_key, T_team, T_user) when lookups
hit DB or cache.
2026-02-05 15:33:44 -08:00
Alexsander Hamir
7cb549acf5 nineth round of measurements 2026-02-05 15:09:11 -08:00
Alexsander Hamir
9e1e0ad8d2 eighth round of measurements 2026-02-05 14:05:55 -08:00
Alexsander Hamir
f4094cefc9 Seventh round of measurements 2026-02-05 12:30:37 -08:00
Alexsander Hamir
2c5d3d98f9 Sixth round of measurements 2026-02-05 12:23:27 -08:00
Alexsander Hamir
19b0ebdea5 Fifth round of measurements 2026-02-05 12:04:23 -08:00
Alexsander Hamir
6fdf6e9f0b Add random id generation to user_id 2026-02-05 11:52:13 -08:00
Alexsander Hamir
cfb13098e7 Fourth round of measurements 2026-02-05 11:40:39 -08:00
Alexsander Hamir
9cfe517d4f Third round of measurements 2026-02-05 10:42:19 -08:00
Alexsander Hamir
75061dc985 Second round of measurements 2026-02-05 09:49:48 -08:00
Alexsander Hamir
956bf16460 LiteLLM configuration file 2026-02-04 17:53:59 -08:00
Alexsander Hamir
8fff99b9d8 Latency repro stats 2026-02-04 17:53:11 -08:00
Alexsander Hamir
12fff07f42 Latency repro file 2026-02-04 17:52:34 -08:00
yuneng-jiang
d2e113111f
Merge pull request #20436 from BerriAI/litellm_search_tools_config_ui
[Feature] UI - Search Tools: Show Config Defined Search Tools
2026-02-04 13:56:19 -08:00
yuneng-jiang
cd9466a50c Adding tests 2026-02-04 12:35:58 -08:00
yuneng-jiang
609c423314 migrate to antd table 2026-02-04 12:22:57 -08:00
yuneng-jiang
208cf5e86d refactor - rename search tools files 2026-02-04 11:53:03 -08:00
yuneng-jiang
a16faa9e0a
Merge pull request #20394 from BerriAI/litellm_spend_fix_2
[Fix] Unique Constraint on Daily Tables + Logging When Updates Fail
2026-02-04 09:42:46 -08:00
Sameer Kankute
8b563a7641
Merge pull request #20402 from BerriAI/litellm_responses_tools_file_ids
Add mapping for responses tools in file ids
2026-02-04 18:09:39 +05:30
Sameer Kankute
8a3b253e62
Merge pull request #20390 from BerriAI/litellm_fix_empty_message
Fix: empty assistant message for converse API
2026-02-04 18:05:37 +05:30
Sameer Kankute
18a524a1dc
Merge pull request #20408 from BerriAI/litellm_fix_model+map_streaming
Fix supports_native_streaming for gemini and vertex ai and claude models
2026-02-04 17:56:48 +05:30
Sameer Kankute
a86e501632
Merge pull request #20407 from BerriAI/litellm_key_mcp_permissions
Add Key info endpoint object permission data
2026-02-04 17:56:05 +05:30
Sameer Kankute
1a5f2a566f Fix: test_bedrock_no_default_message 2026-02-04 17:52:28 +05:30
Sameer Kankute
b2feedc469
Merge pull request #20318 from BerriAI/litellm_oss_staging_02_03_2026
feat(guardrails): implement team-based isolation guardrails mgmnt (#1…
2026-02-04 17:49:30 +05:30
Sameer Kankute
54b5c7d2cd Fix: litellm/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_grayswan.py 2026-02-04 17:35:26 +05:30
Sameer Kankute
f8b6af5577 Fix test_transform_messages_disable_copilot_system_to_assistant 2026-02-04 17:29:55 +05:30
Sameer Kankute
674593e4d7
Merge pull request #20413 from BerriAI/revert-20145-fix/proxy_failure_cases
Revert "fix: proxy failure cases, now log ip and user agent, key hash, name"
2026-02-04 17:17:39 +05:30
Sameer Kankute
6b25e37309
Revert "fix: proxy failure cases, now log ip and user agent, key hash, name (…"
This reverts commit ec279eb426.
2026-02-04 17:16:51 +05:30
Sameer Kankute
5cec5c3bef fix model map json 2026-02-04 14:48:49 +05:30
Sameer Kankute
0ed5e51f9b Fix supports_native_streaming for anthropic models 2026-02-04 14:44:31 +05:30
Sameer Kankute
20c21c63d9 Fix supports_native_streaming for gemini and vertex ai models 2026-02-04 14:41:32 +05:30
Sameer Kankute
fc873d8867 Fix mypy issues 2026-02-04 14:40:08 +05:30
Sameer Kankute
42561729ee Add Key info endpoint object permission data 2026-02-04 14:21:19 +05:30
Sameer Kankute
bfc0c4b4ab
Merge pull request #20396 from BerriAI/litellm_copilot_kit_sdk
[DOCS]Add copilotkit sdk doc as supported agents sdk
2026-02-04 13:41:08 +05:30
Sameer Kankute
4d90767d82
Merge pull request #20406 from BerriAI/litellm_deepreasearch_agent_gemini
Add gemini deep research in model cost map
2026-02-04 13:39:55 +05:30
Sameer Kankute
216cf4cac5 Add gemini deep research in model cost map 2026-02-04 13:38:13 +05:30
Sameer Kankute
e4c1cfff9d Fix mypy issues 2026-02-04 13:25:21 +05:30
Sameer Kankute
2698c9218c Fix mypy issues 2026-02-04 13:24:00 +05:30
Sameer Kankute
5413f584f5 Fix code quality issues 2026-02-04 13:17:05 +05:30
Sameer Kankute
8b3213ce5c Add mapping for responses tools in file ids 2026-02-04 13:12:45 +05:30
Sameer Kankute
cdd4569064
Apply suggestion from @greptile-apps[bot]
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-02-04 11:56:17 +05:30
Sameer Kankute
465bbf3514 Add copilotkit sdk doc as supported agents sdk 2026-02-04 11:53:49 +05:30
Sameer Kankute
8109413a54 Add copilotkit sdk doc as supported agents sdk 2026-02-04 11:52:17 +05:30
Krish Dholakia
58cc6248ab
Skip test_e2e_semantic_filter when OPENAI_API_KEY is not set (#20387)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-02-03 22:09:47 -08:00
Krish Dholakia
ca34b4ee13
Revert "feat(guardrails): implement team-based isolation guardrails mgmnt (#1…" (#20393)
This reverts commit 76a399ba69.
2026-02-03 20:55:46 -08:00
yuneng-jiang
9ce55057ab Adding logging for when batching fails 2026-02-03 20:54:40 -08:00
Krrish Dholakia
49c678589e fix: fix schema.prisma on litellm proxy extras 2026-02-03 20:36:10 -08:00
yuneng-jiang
30027d2928 save empty endpoint as string 2026-02-03 20:26:57 -08:00
Sameer Kankute
15351a93dc Fix: empty assistant message for converse API 2026-02-04 09:50:58 +05:30